© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 12-RES-JB
    11. 2736
    Prev
    Next
    INDEX
    Explanations

    information related to criminal activities and law enforcement.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    statements of fact or refutation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whilst
    -1.26
     realise
    -1.11
     ',
    -1.10
    Firstly
    -1.09
     recognise
    -1.00
     Firstly
    -0.99
     whilst
    -0.99
    "]=>
    -0.96
     apologise
    -0.95
     util
    -0.94
    POSITIVE LOGITS
     Haitian
    1.66
     Haiti
    1.49
     Guatem
    1.48
     Hait
    1.46
     Hond
    1.41
     Nicarag
    1.37
     Honduras
    1.34
     Tunis
    1.30
     Colombian
    1.30
     Ethiopian
    1.30
    Activations Density 1.130%

    No Known Activations